Model Terminal
Parakeet TDT 0.6B v2
NVIDIA Parakeet TDT 0.6B v2 is a 600-million-parameter English automatic speech recognition model that converts spoken audio into text with punctuation, capitalization, and word-level timestamps. It is optimized for high-speed, low-error transcription of audio up to 24 minutes and is deployable via NVIDIA NIM. Source: supabase.
Value score
Not scored
Context
—
tokens
Max output
—
tokens
Price
—
Capability radar
Peer value bars
Identity
- Developer
- NVIDIA
- Openness
- —
- Modalities
- —
- Release
- —
- Knowledge cutoff
- —
- Deprecation
- —
- API docs
- —
Benchmarks
No benchmark scores yet.
Compare nearby
Pricing
- Input / 1M
- —
- Output / 1M
- —
- Speed
- —